Deep learning has emerged as a powerful tool in various domains, revolutionising machine
learning research. However, one persistent challenge is the scarcity of labelled training …

The performance of spoofing countermeasure systems depends fundamentally upon the use
of sufficiently representative training data. With this usually being limited, current solutions …

For speaker recognition, it is difficult to extract an accurate speaker representation from
speech because of its mixture of speaker traits and content. This paper proposes a …

The speech representations learned from large-scale unlabeled data have shown better
generalizability than those from supervised learning and thus attract a lot of interest to be …

In recent years, speaker recognition systems based on raw waveform inputs have received
increasing attention. However, the performance of such systems are typically inferior to the …

Speaker individuality information is among the most critical elements within speech signals.
By thoroughly and accurately modeling this information, it can be utilized in various …

The third instalment of the VoxCeleb Speaker Recognition Challenge was held in
conjunction with Interspeech 2021. The aim of this challenge was to assess how well current …

Speaker modeling plays a crucial role in various tasks, and fixed-dimensional vector
representations, known as speaker embeddings, are the predominant modeling approach …

In self-supervised learning for speaker recognition, pseudo labels are useful as the
supervision signals. It is a known fact that a speaker recognition model doesn't always …

The automatic speaker verification task has achieved great success using deep learning
approaches with a large-scale, manually annotated dataset. However, collecting a …